CoolFace
Modelpublic

pyaging/phenoage

sourceHugging Facemitupdated 1mo agoView on Hugging Face
0likes709downloads
Model Card

phenoage

Clinical Phenotypic Age combines chronological age with nine blood biomarkers selected by penalized mortality regression and expresses mortality risk as an equivalent age in years. C-reactive protein is supplied raw in mg/dL and natural-log-transformed inside the clock, with readings at or below 0.01 mg/dL clamped to that floor; before pyaging 0.5.0 the feature was named log_crp and the caller had to supply the log. Continuing to pass a pre-logged value biases the estimate downward: any pre-logged CRP below 1.01 mg/dL, which covers most healthy adults, lands on the clamp floor and returns the same answer as omitting CRP entirely — about four years younger than the correct value for a typical adult, so the estimate reads healthier than it is.

Predictsphenotypic age
SpeciesHomo sapiens
Tissueblood
Data typeclinical biomarkers
Model typepenalized hazards regression with Gompertz calibration
Year2018

Use with pyaging

python
import pyaging as pya

pya.pred.predict_age(adata, ["phenoage"])

Browse every clock in the pyaging Clock Catalogue.

Citation

Levine, M. E., et al. "An epigenetic biomarker of aging for lifespan and healthspan." Aging 10.4 (2018): 573-591.

https://doi.org/10.18632/aging.101414